Predictive modeling platform for serial casting to correct orthopedic deformities

Abstract

A system and method are provided herein for modeling of force vectors for serial casts to correct orthopedic deformities includes a camera configured to capture a three-dimensional image of the deformity, a computing device programmed to generate a three-dimensional model of the deformity based on the image of the deformity, determine the boundary conditions for the deformity based on the three-dimensional image of the deformity, and generate force vectors for a series of casts to correct the deformity. In exemplary embodiments, the system can print a series of casts to correct the deformity.

What is claimed is: 
     
       1. A system for modeling of force vectors for a cast to correct an orthopedic deformity, the system comprising:
 a processor programmable to execute machine readable instructions on one or more non-transitory media holding the machine readable instructions, the processor configured to:
 receive an image of the deformity; 
 generate a three-dimensional model of the deformity based on the image of the deformity; 
 determine boundary conditions of the deformity using a machine learning model executable by the processor, wherein the machine learning model is trained using a corpus of prior images of orthopedic deformities of patients; 
 simulate, using a finite element analysis, an application of a force vector to the three-dimensional model of the deformity and the effect thereon on points of support; and 
 generate a set of force vectors for a cast based on a series of automated finite-element-analysis simulations to minimize a deviation from the determined boundary condition. 
 
 
     
     
       2. The system of  claim 1 , wherein the corpus of prior images of the orthopedic deformity of patients includes an uncorrected image of the deformity of the patients, one or more intermediate images of the deformity of the patients and an image of the final corrected deformity of the patient. 
     
     
       3. The system of  claim 1 , wherein the system includes a camera. 
     
     
       4. The system of  claim 3 , wherein the camera is at least one of, an array of cameras, an ultrasound, a three-dimensional scanner, an magnetic resonance imaging device, or a CT scanner. 
     
     
       5. The system of  claim 1 , wherein the corpus of prior images of patients includes a plurality of scans of prior discarded casts of patients to determine the original deformity, the stages of correction of the deformity and the final corrected deformity. 
     
     
       6. The system of  claim 1 , wherein to generate the set force vectors for the cast the system is programmed to:
 process the finite element analysis based on force vectors that correspond to one or more points in a point cloud of the deformity generated from one or more prior simulations for a plurality of patients; and 
 determine the set of force vectors for the cast using the finite element analysis. 
 
     
     
       7. The system of  claim 1 , wherein to generate the set force vectors for the cast the system is programmed to:
 correct the deformity in more than one direction in the cast simultaneously. 
 
     
     
       8. The system of  claim 1 , wherein to generate the set force vectors for the cast the system is programmed to:
 correct the deformity simultaneously in three dimensions for each plane of correction. 
 
     
     
       9. A method for modeling of force vectors for serial casts to correct orthopedic deformities, the method comprising:
 receiving, via a computing device, an image of the deformity; 
 generating, via the computing device, a three-dimensional model of the deformity based on the image of the deformity; 
 determining, via the computing device, boundary conditions of the deformity using a machine learning model, the machine learning model is trained using a corpus of prior images of orthopedic deformities of patients or prior images of casts used to correct orthopedic deformities of the patients; 
 simulating, using a finite element analysis, via the computing device, an application of a force vector to the three-dimensional model of the deformity and the effect thereon on points of support; and 
 generating, via the computing device, a set force vectors for a cast based on a series of automated finite-element-analysis simulations to minimize a deviation from the determined boundary condition. 
 
     
     
       10. The method of  claim 9 , wherein the image of the deformity is acquired via a camera. 
     
     
       11. The method of  claim 10 , wherein the camera is at least one of an array of cameras, an ultrasound, a three-dimensional scanner, an magnetic resonance imaging device, or a CT scanner. 
     
     
       12. The method of  claim 9 , wherein the corpus of prior images of patients includes a plurality of scans of prior discarded casts of patients to determine the original deformity, the stages of correction of the deformity and the final corrected deformity. 
     
     
       13. The method of  claim 9 , wherein the method further comprises:
 processing the finite element analysis based on force vectors that correspond to one or more points in a point cloud of the deformity based on prior simulations for a plurality of patients. 
 
     
     
       14. A non-transitory computer readable medium storing instructions executable by a processing device, wherein execution of the instructions causes the processing device to implement a method for modeling of force vectors for a cast to correct an orthopedic deformities, the method comprising:
 generating, via the computing device, a three-dimensional model of the deformity based on the image of the deformity; 
 determining, via the computing device, boundary conditions of the deformity using a machine learning model, wherein the machine learning model is trained using a corpus of prior images of orthopedic deformities of patients; 
 simulating, using a finite element analysis, via the computing device, an application of a force vector to the three-dimensional model of the deformity and the effect thereon on points of support; and 
 generating, via the computing device, a set of force vectors for a cast based on a series of automated finite-element-analysis simulations to minimize a deviation from the determined boundary condition.